Memori - Automatic Long-term Memory for OpenClaw
Persistent memory integration that works automatically in the background. No commands, no manual management - just install and your agent remembers.
Core Workflow
Memori operates automatically via OpenClaw lifecycle hooks:
Before Each Response (Intelligent Recall)
Memori automatically:
- 1. Searches for relevant past conversations
- Injects matching context into the agent's prompt
- Enables continuity across sessions - no search command needed
After Each Response (Advanced Augmentation)
Memori automatically:
- 1. Captures the conversation turn (user + assistant)
- Sends to Memori backend for intelligent processing
- Extracts facts, deduplicates, and indexes - no storage command needed
You don't manage memory - it just works.
Installation
CODEBLOCK0
Configuration
Add to your ~/.openclaw/openclaw.json:
CODEBLOCK1
Configuration Options
- - apiKey (required): Your Memori API key from memorilabs.ai
- entityId (required): Unique identifier for this user's memories
Get your API key: https://app.memorilabs.ai/signup
How It Works
Memori uses OpenClaw lifecycle hooks for automatic operation:
CODEBLOCK2
Zero commands needed - memory works automatically in the background.
What Memori Does Automatically
Backend Intelligence (handled by Memori SDK):
- - Intelligent fact extraction from conversations
- Automatic deduplication and merging
- Semantic ranking by relevance
- Temporal decay (older memories fade)
- Privacy filtering (no secrets stored)
Plugin Role (what runs in OpenClaw):
- - Pipes conversations to Memori backend
- Injects recalled memories into prompts
- Zero configuration after setup
You don't configure what to capture - the backend handles it.
Verification
Check that the plugin is working:
CODEBLOCK3
Quota Management
Check your current API quota:
CODEBLOCK4
Example output:
CODEBLOCK5
Use this to monitor usage and upgrade if needed.
Performance
- - Automatic deduplication prevents memory bloat
- Semantic ranking ensures relevant memories surface first
- Zero manual commands - always-on background operation
Privacy & Data Handling
Transparent data flow:
- - ✅ Conversations sent to Memori backend (https://api.memorilabs.ai)
- ✅ Data encrypted in transit and at rest
- ✅ You control data via your API key and entityId
- ✅ Delete memories anytime via Memori dashboard
- ✅ No third-party sharing
- ⚠️ Only install if you trust Memori with conversation data
Backend automatically filters sensitive data (API keys, passwords, secrets).
For details: Memori Privacy Policy
Memory Persistence
Memories persist across:
- - Session restarts
- Gateway restarts
- System reboots
- OpenClaw upgrades
All storage handled by Memori backend - no local database needed.
Troubleshooting
Plugin not loading:
- - Verify
enabled: true in openclaw.json - Check API key: INLINECODE2
- Restart gateway: INLINECODE3
No memories captured:
- - Check gateway logs for
[Memori] errors - Verify API endpoint reachable
- Test API key: INLINECODE5
Memories not recalled:
- - Ensure
entityId is consistent across sessions - Verify memories exist:
memori quota shows count > 0 - Check logs for recall errors
Quota exceeded:
- - Run
memori quota to check usage - Upgrade at memorilabs.ai
- Or clear old memories via dashboard
Learn More
- - npm Package: https://www.npmjs.com/package/@memorilabs/openclaw-memori
- GitHub: https://github.com/MemoriLabs/Memori
- Documentation: https://memorilabs.ai/docs/memori-cloud/openclaw/overview/
- API Dashboard: https://app.memorilabs.ai/
- Support: GitHub Issues
Notes
This skill teaches the agent about the Memori plugin. The plugin must be installed separately via npm. Once installed, memory capture and recall happen automatically - no commands needed.
Memori - OpenClaw的自动长期记忆
在后台自动运行的持久化记忆集成。无需命令，无需手动管理——只需安装，你的智能体就能记住。
核心工作流程
Memori通过OpenClaw生命周期钩子自动运行：
每次响应前（智能回忆）
Memori自动：
- 1. 搜索相关的历史对话
- 将匹配的上下文注入智能体的提示词中
- 实现跨会话的连续性——无需搜索命令
每次响应后（高级增强）
Memori自动：
- 1. 捕获对话轮次（用户+助手）
- 发送至Memori后端进行智能处理
- 提取事实、去重并建立索引——无需存储命令
你无需管理记忆——它自动运行。
安装
bash
openclaw plugins install @memorilabs/openclaw-memori
配置
添加到你的 ~/.openclaw/openclaw.json：
json
{
plugins: {
entries: {
openclaw-memori: {
enabled: true,
config: {
apiKey: ${MEMORIAPIKEY},
entityId: openclaw-user
}
}
}
}
}
配置选项
- - apiKey（必填）：来自 memorilabs.ai 的 Memori API 密钥
- entityId（必填）：该用户记忆的唯一标识符
获取你的 API 密钥：https://app.memorilabs.ai/signup
工作原理
Memori使用OpenClaw生命周期钩子自动运行：
javascript
beforepromptbuild → 智能回忆（注入相关记忆）
agent_end → 高级增强（存储对话轮次）
零命令需求——记忆在后台自动运行。
Memori自动完成的功能
后端智能（由Memori SDK处理）：
- - 从对话中智能提取事实
- 自动去重与合并
- 按相关性进行语义排序
- 时间衰减（旧记忆逐渐淡出）
- 隐私过滤（不存储机密信息）
插件角色（在OpenClaw中运行）：
- - 将对话传输至Memori后端
- 将回忆到的记忆注入提示词
- 设置后零配置
你无需配置要捕获的内容——后端会自动处理。
验证
检查插件是否正常运行：
bash
验证插件已安装
openclaw plugins list
在网关输出中检查Memori日志
查找以 [Memori] 为前缀的条目
配额管理
检查当前API配额：
bash
memori quota
示例输出：
_
| \/ | ()
| |\/| |/ \ \ / \| | |
| | | | / | | | | | (_) | | | |
|| ||\|| || ||\/|| |_|
perfectam memoriam
memorilabs.ai
+ 最大记忆数：100
+ 当前记忆数：0
+ 你当前未超出配额。
使用此命令监控使用情况，并在需要时升级。
性能
- - 自动去重防止记忆膨胀
- 语义排序确保相关记忆优先呈现
- 零手动命令——始终在后台运行
隐私与数据处理
透明的数据流：
- - ✅ 对话发送至Memori后端（https://api.memorilabs.ai）
- ✅ 传输和存储数据均加密
- ✅ 通过API密钥和entityId控制数据
- ✅ 随时通过Memori仪表盘删除记忆
- ✅ 不与第三方共享
- ⚠️ 仅在信任Memori处理对话数据时安装
后端自动过滤敏感数据（API密钥、密码、机密信息）。
详情请参阅：Memori隐私政策
记忆持久性
记忆在以下情况下保持持久：
所有存储由Memori后端处理——无需本地数据库。
故障排除
插件未加载：
- - 验证 openclaw.json 中 enabled: true
- 检查API密钥：echo $MEMORIAPIKEY
- 重启网关：openclaw gateway restart
未捕获记忆：
- - 检查网关日志中的 [Memori] 错误
- 验证API端点可访问
- 测试API密钥：memori quota
未回忆记忆：
- - 确保 entityId 在会话间保持一致
- 验证记忆存在：memori quota 显示计数 > 0
- 检查日志中的回忆错误
配额超出：
了解更多
- - npm包：https://www.npmjs.com/package/@memorilabs/openclaw-memori
- GitHub：https://github.com/MemoriLabs/Memori
- 文档：https://memorilabs.ai/docs/memori-cloud/openclaw/overview/
- API仪表盘：https://app.memorilabs.ai/
- 支持：GitHub Issues
备注
此技能向智能体介绍Memori插件。该插件需通过npm单独安装。安装后，记忆捕获和回忆将自动进行——无需任何命令。
